Prediction of Area and Production of Groundnut Using Box-Jenkins Arima and Neural Network Approach

  • S. T. Pavana Kumar College of Community Science, Central Agricultural University, Tura, Meghalaya-794005, India
  • Ferdinand B. Lyngdoh College of Community Science, Central Agricultural University, Tura, Meghalaya-794005, India
Keywords: Groundnut data, Box-Jenkins models, neural network, model accuracy, parameters

Abstract

Selection of parameters for Auto Regressive Integrated Moving Average (ARIMA) model in the prediction process is one of the most important tasks. In the present study, groundnut data was utlised to decide appropriate p, d, q parameters for ARIMA model for the prediction purpose. Firstly, the models were fit to data without splitting into training and validation/testing sets and evaluated for their efficiency in predicting the area and production of groundnut over the years. Meanwhile, models are compared among other fitted ARIMA models with different p, d, q parameters based on decision criteria’s viz., ME, RMSE, MAPE, AIC, BIC and R-Square. The ARIMA model with parameters p-2 d-1-2, q-1-2 are found adequate in predicting the area as well as production of groundnut. The model ARIMA (2, 2, 2) and ARIMA (2,1,1) predicted the area of groundnut crop with minimum error estimates and residual characteristics (ei). The models were fit into split data i.e., training and test data set, but these models’ prediction power (R-Square) declined during testing. In case of predicting the area, ARIMA (2,2,2) was consistent over the split data but it was not consistent while predicting the production over years. Feed-forward neural networks with single hidden layer were fit to complete, training and split data. The neural network models provided better estimates compared to Box-Jenkins ARIMA models. The data was analysed using R-Studio.

Author Biographies

S. T. Pavana Kumar, College of Community Science, Central Agricultural University, Tura, Meghalaya-794005, India

S. T. Pavan Kumar is an Assistant Professor (Statistics) at College of Community Science, Central Agricultural University (Imphal), Tura, Meghalaya. He attended the Bidhan Chandra Krishi Viswavisyalaya, West Bengal, from where he received Ph.D (Agricultural Statitsics) in the year 2017. He published 12 research articles and chapters in the field of statistics in the national, international journals and training manuals.

Ferdinand B. Lyngdoh, College of Community Science, Central Agricultural University, Tura, Meghalaya-794005, India

Ferdinand B. Lyngdoh is an Assistant Professor (English) at College of Community Science, Central Agricultural University (Imphal), Tura, Meghalaya. He is currently pursuing his doctoral degree from the North Eastern Hill University (NEHU), Tura Campus.

Published
2020-12-30
Section
Articles